## What type of PR is this? (check all applicable)
- [ ] Refactor
- [ ] Feature
- [ X] Bug Fix
- [ ] Optimization
- [ ] Documentation Update
- [ ] Community Node Submission
## Have you discussed this change with the InvokeAI team?
- [X ] Yes
- [ ] No, because:
## Have you updated all relevant documentation?
- [ ] Yes
- [X ] Not needed
## Description
This bugfix enables InvokeAI to convert sd-1, sd-2 and sdxl base model
checkpoints (.safetensors) to diffusers.
## What type of PR is this? (check all applicable)
- [ ] Refactor
- [ ] Feature
- [ ] Bug Fix
- [ X] Optimization
- [ ] Documentation Update
- [ ] Community Node Submission
## Have you discussed this change with the InvokeAI team?
- [ X] Yes
- [ ] No, because:
## Have you updated all relevant documentation?
- [ ] Yes
- [X ] No
## Description
This PR causes the installer to install, by default, the fine-tuned
SDXL-1.0 VAE located at
https://huggingface.co/madebyollin/sdxl-vae-fp16-fix.
Although this VAE is supposed to run at fp16 resolution, currently it
only works in InvokeAI at fp32. However, because it is a fine tune, it
may have fewer of the watermark-related artifacts that we see with the
SDXL-1.0 VAE.
## What type of PR is this? (check all applicable)
- [ ] Refactor
- [ ] Feature
- [ X] Bug Fix
- [ ] Optimization
- [ ] Documentation Update
- [ ] Community Node Submission
## Have you discussed this change with the InvokeAI team?
- [ X] Yes
- [ ] No, because:
## Have you updated all relevant documentation?
- [ ] Yes
- [ X] Not necessary
## Description
When adding new core models to a 3.0.0 root directory needed to support
SDXL, the configure script was (under some conditions) overwriting
models.yaml. This PR corrects the problem.
## What type of PR is this? (check all applicable)
- [ ] Refactor
- [ ] Feature
- [X ] Bug Fix
- [ ] Optimization
- [ ] Documentation Update
- [ ] Community Node Submission
## Have you discussed this change with the InvokeAI team?
- [ X] Yes
- [ ] No, because:
## Have you updated all relevant documentation?
- [X ] Yes
- [ ] No
## Description
I have reworked the console TUIs for the configure and model install
scripts to require much less vertical space. In the event that the
"NEXT" button is still missing and "page 1/2" is displayed, scrolling
beyond the last checkbox will now automatically move to page 2 where the
buttons are displayed. This is not ideal, but will no longer block user
completely.
If users continue to have problems after this, I'll get rid of the TUI
altogether and replace with a web form.
## Added/updated tests?
- [ ] Yes
- [X ] No : not needed
## [optional] Are there any post deployment tasks we need to perform?
## What type of PR is this? (check all applicable)
- [ ] Refactor
- [ ] Feature
- [ ] Bug Fix
- [ ] Optimization
- [X ] Documentation Update
- [ ] Community Node Submission
## Have you discussed this change with the InvokeAI team?
- [ ] Yes
- [X ] No, because they trust me
## Have you updated all relevant documentation?
- [ X] Yes
- [ ] No
## Description
* Added the RAIL++ license for SDXL
* Updated configure script with URLs for both the original RAIL-M and
RAIL++ licenses
* Added invisible watermark documentation and renamed doc file
* Updated documentation for installation
* Updated documentation on settings in invokeai.yaml
## What type of PR is this? (check all applicable)
- [ ] Refactor
- [ ] Feature
- [x] Bug Fix
- [ ] Optimization
- [ ] Documentation Update
- [ ] Community Node Submission
## Have you discussed this change with the InvokeAI team?
- [ ] Yes
- [ ] No, because:
## Have you updated all relevant documentation?
- [ ] Yes
- [ ] No
## Description
Metadata was not getting saved coz the accumulator was not plugged in if
watermark or nsfw nodes were turned off.
## Related Tickets & Documents
<!--
For pull requests that relate or close an issue, please include them
below.
For example having the text: "closes #1234" would connect the current
pull
request to issue 1234. And when we merge the pull request, Github will
automatically close the issue.
-->
- Related Issue #
- Closes #
## QA Instructions, Screenshots, Recordings
<!--
Please provide steps on how to test changes, any hardware or
software specifications as well as any other pertinent information.
-->
## Added/updated tests?
- [ ] Yes
- [ ] No : _please replace this line with details on why tests
have not been included_
## [optional] Are there any post deployment tasks we need to perform?
## What type of PR is this? (check all applicable)
- [ ] Refactor
- [ ] Feature
- [x ] Bug Fix
- [ ] Optimization
- [ ] Documentation Update
- [ ] Community Node Submission
## Have you discussed this change with the InvokeAI team?
- [ ] Yes
- [ x] No, because there was no time!
## Have you updated all relevant documentation?
- [ ] Yes
- [X ] No
## Description
Hotfix for issue of SD1 and SD2 legacy safetensors models not converting
in 3.0.1rc1.
## What type of PR is this? (check all applicable)
- [ ] Refactor
- [ ] Feature
- [ ] Bug Fix
- [ ] Optimization
- [ ] Documentation Update
- [ ] Community Node Submission
## Have you discussed this change with the InvokeAI team?
- [ ] Yes
- [ ] No, because:
## Have you updated all relevant documentation?
- [ ] Yes
- [ ] No
## Description
## Related Tickets & Documents
<!--
For pull requests that relate or close an issue, please include them
below.
For example having the text: "closes #1234" would connect the current
pull
request to issue 1234. And when we merge the pull request, Github will
automatically close the issue.
-->
- Related Issue #
- Closes #
## QA Instructions, Screenshots, Recordings
<!--
Please provide steps on how to test changes, any hardware or
software specifications as well as any other pertinent information.
-->
## Added/updated tests?
- [ ] Yes
- [ ] No : _please replace this line with details on why tests
have not been included_
## [optional] Are there any post deployment tasks we need to perform?
## What type of PR is this? (check all applicable)
- [ ] Refactor
- [ X] Feature
- [ ] Bug Fix
- [ ] Optimization
- [ ] Documentation Update
- [ ] Community Node Submission
## Have you discussed this change with the InvokeAI team?
- [ X] Yes
- [ ] No, because:
## Have you updated all relevant documentation?
- [X ] Yes
- [] No
## Description
This PR adds NSFW checker and invisible watermark fields. The NSFW
checker takes an image input and produces an image output. If NSFW
content is detected, the output image will be blurred and a "caution"
icon pasted into its upper left corner. A boolean `active` field
controls whether the checker is active. If turned off it simply returns
a copy of the image.
The invisible watermark node adds an invisible text to the image,
defaulting to "InvokeAI". To decode the watermark use the
`invisible-watermark` command, which is part of the
`invisible-watermark` library:
```
$ invisible-watermark -v -a decode -t bytes -m dwtDct -l 64 ./bluebird-watermark.png
decode time ms: 14.129877090454102
InvokeAI
```
Note that the `-l` (length) argument is mandatory. It is set to 64 here
because the watermark `InvokeAI` is 8 bytes/64 bits long. The length
must match in order for the watermark to be decoded correctly.
Both nodes are now incorporated into the linear Text2Image and
Image2Image UIs, including the canvas. They are not implemented for
inpaint currently.
The nodes can be disabled with configuration options:
```
invisible_watermark: false
nsfw_checker: false
```
or at launch time with `--no-invisible_watermark` and
`--no-nsfw_checker`.
